An intelligent virtual metrology system with adaptive update for semiconductor manufacturing

Seokho Kang, Pilsung Kang

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Virtual metrology involves the estimation of metrology values using a prediction model instead of metrological equipment, thereby providing an efficient means for wafer-to-wafer quality control. Because wafer characteristics change over time according to the influence of several factors in the manufacturing process, the prediction model should be suitably updated in view of recent actual metrology results. This gives rise to a trade-off relationship, as more frequent updates result in a higher accuracy for virtual metrology, while also incurring a heavier cost in actual metrology. In this paper, we propose an intelligent virtual metrology system to achieve a superior metrology performance with lower costs. By employing an ensemble of artificial neural networks as the prediction model, the prediction, reliability estimation, and model update are successfully integrated into the proposed virtual metrology system. In this system, actual metrology is only performed for those wafers where the current prediction model cannot perform reliable predictions. When actual metrology is performed, the prediction model is instantly updated to incorporate the results. Consequently, the actual metrology ratio is automatically adjusted according to the corresponding circumstances. We demonstrate the effectiveness of the method through experimental validation on actual datasets.

Original languageEnglish
Pages (from-to)66-74
Number of pages9
JournalJournal of Process Control
Volume52
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

Semiconductor Manufacturing
Metrology
Update
Semiconductor materials
Prediction Model
Wafer
Reliability Estimation
Prediction
Experimental Validation
Quality Control
Quality control
Artificial Neural Network
Costs
High Accuracy
Ensemble
Manufacturing
Trade-offs

Keywords

  • Adaptive update
  • Reliability estimation
  • Semiconductor manufacturing
  • Virtual metrology

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

An intelligent virtual metrology system with adaptive update for semiconductor manufacturing. / Kang, Seokho; Kang, Pilsung.

In: Journal of Process Control, Vol. 52, 01.01.2017, p. 66-74.

Research output: Contribution to journalArticle

@article{0f267de86b2b4ee29d13cfdf0072d5ac,
title = "An intelligent virtual metrology system with adaptive update for semiconductor manufacturing",
abstract = "Virtual metrology involves the estimation of metrology values using a prediction model instead of metrological equipment, thereby providing an efficient means for wafer-to-wafer quality control. Because wafer characteristics change over time according to the influence of several factors in the manufacturing process, the prediction model should be suitably updated in view of recent actual metrology results. This gives rise to a trade-off relationship, as more frequent updates result in a higher accuracy for virtual metrology, while also incurring a heavier cost in actual metrology. In this paper, we propose an intelligent virtual metrology system to achieve a superior metrology performance with lower costs. By employing an ensemble of artificial neural networks as the prediction model, the prediction, reliability estimation, and model update are successfully integrated into the proposed virtual metrology system. In this system, actual metrology is only performed for those wafers where the current prediction model cannot perform reliable predictions. When actual metrology is performed, the prediction model is instantly updated to incorporate the results. Consequently, the actual metrology ratio is automatically adjusted according to the corresponding circumstances. We demonstrate the effectiveness of the method through experimental validation on actual datasets.",
keywords = "Adaptive update, Reliability estimation, Semiconductor manufacturing, Virtual metrology",
author = "Seokho Kang and Pilsung Kang",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.jprocont.2017.02.002",
language = "English",
volume = "52",
pages = "66--74",
journal = "Journal of Process Control",
issn = "0959-1524",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - An intelligent virtual metrology system with adaptive update for semiconductor manufacturing

AU - Kang, Seokho

AU - Kang, Pilsung

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Virtual metrology involves the estimation of metrology values using a prediction model instead of metrological equipment, thereby providing an efficient means for wafer-to-wafer quality control. Because wafer characteristics change over time according to the influence of several factors in the manufacturing process, the prediction model should be suitably updated in view of recent actual metrology results. This gives rise to a trade-off relationship, as more frequent updates result in a higher accuracy for virtual metrology, while also incurring a heavier cost in actual metrology. In this paper, we propose an intelligent virtual metrology system to achieve a superior metrology performance with lower costs. By employing an ensemble of artificial neural networks as the prediction model, the prediction, reliability estimation, and model update are successfully integrated into the proposed virtual metrology system. In this system, actual metrology is only performed for those wafers where the current prediction model cannot perform reliable predictions. When actual metrology is performed, the prediction model is instantly updated to incorporate the results. Consequently, the actual metrology ratio is automatically adjusted according to the corresponding circumstances. We demonstrate the effectiveness of the method through experimental validation on actual datasets.

AB - Virtual metrology involves the estimation of metrology values using a prediction model instead of metrological equipment, thereby providing an efficient means for wafer-to-wafer quality control. Because wafer characteristics change over time according to the influence of several factors in the manufacturing process, the prediction model should be suitably updated in view of recent actual metrology results. This gives rise to a trade-off relationship, as more frequent updates result in a higher accuracy for virtual metrology, while also incurring a heavier cost in actual metrology. In this paper, we propose an intelligent virtual metrology system to achieve a superior metrology performance with lower costs. By employing an ensemble of artificial neural networks as the prediction model, the prediction, reliability estimation, and model update are successfully integrated into the proposed virtual metrology system. In this system, actual metrology is only performed for those wafers where the current prediction model cannot perform reliable predictions. When actual metrology is performed, the prediction model is instantly updated to incorporate the results. Consequently, the actual metrology ratio is automatically adjusted according to the corresponding circumstances. We demonstrate the effectiveness of the method through experimental validation on actual datasets.

KW - Adaptive update

KW - Reliability estimation

KW - Semiconductor manufacturing

KW - Virtual metrology

UR - http://www.scopus.com/inward/record.url?scp=85013218884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013218884&partnerID=8YFLogxK

U2 - 10.1016/j.jprocont.2017.02.002

DO - 10.1016/j.jprocont.2017.02.002

M3 - Article

AN - SCOPUS:85013218884

VL - 52

SP - 66

EP - 74

JO - Journal of Process Control

JF - Journal of Process Control

SN - 0959-1524

ER -